From f8d90e92ce791650dc89944fca009fc36d9e3a90 Mon Sep 17 00:00:00 2001 From: Yury Melnichek Date: Mon, 17 Sep 2012 12:12:12 +0200 Subject: [PATCH] [crawler] Handle correctly paths with symbols '(' and ')'. --- crawler/wikitravel-optimize-articles.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/crawler/wikitravel-optimize-articles.py b/crawler/wikitravel-optimize-articles.py index 07c0166c78..afa7c5d71b 100755 --- a/crawler/wikitravel-optimize-articles.py +++ b/crawler/wikitravel-optimize-articles.py @@ -7,6 +7,9 @@ import sys myPath = os.path.dirname(os.path.realpath(__file__)) +def formatPath(s): + return s.replace('(', '\\(').replace(')', '\\)') + for i, line in enumerate(sys.stdin): (url, title, fileBase) = json.loads(line) fileName = fileBase + '.article' @@ -19,4 +22,6 @@ for i, line in enumerate(sys.stdin): '--remove-intertag-spaces --simple-bool-attr --remove-quotes ' '--remove-js-protocol --type html ' '-o {outFileName} {fileName}' - .format(myPath = myPath, fileName = fileName, outFileName = outFileName)) + .format(myPath = myPath, + fileName = formatPath(fileName), + outFileName = formatPath(outFileName)))